Call for contributors!

[PaParaZz1]

Introduction

Dear community,

🚀 DI-engine aims to be a generalized decision intelligence engine, including various algorithm toolkits and application demonstrations. Due to the complexity of abstraction and maintainment, DI-engine has become a pretty big beast 🐲.
🌟 Therefore, We are calling for contributors now. For each applied task, we will arrange a internal support to help and review related work. We are looking forward to more support and inspiration from open-source community~

🏁 Here we list different types of tasks below:

Algorithm Section

No.	Task Name	Difficulty	Assigned to	Supporter	Status	Other Info
1	nstep/td-lambda support for SAC	⭐⭐	@GoingMyWay	@PaParaZz1	Apply
2	optimal baseline for MAPPO	⭐⭐
3	DRL algo: MPO	⭐⭐⭐
4	multi-agent RL algo: QPLEX	⭐⭐⭐
5	other RL algo: JSRL	⭐⭐⭐⭐

Env and Application Section

No.	Task Name	Difficulty	Assigned to	Supporter	Status	Other Info
1	Integration for metaworld	⭐⭐
2	Update for competitive-rl	⭐⭐
3	Integration for GNN + RL	⭐⭐
4	Integration for RL4LM	⭐⭐⭐
5	Integration for BabyAI	⭐⭐⭐

Doc and Tutorial Section

No.	Task Name	Difficulty	Assigned to	Supporter	Status	Other Info
1	English translation for MDQN doc	⭐	@TuTuHuss	@ruoyuGao	Finish	opendilab/DI-engine-docs#232
2	English translation for bitfilp doc	⭐	@deepNet-Chirag	@zjowowen	Finish	opendilab/DI-engine-docs#235
3	English translation for Acrobot doc	⭐	@deepNet-Chirag	@puyuan1996	Apply
4	Chinese translation for PPG doc	⭐	@PommesPeter	@zjowowen	Finish	opendilab/DI-engine-docs#260
5	Chinese translation for IMPALA doc	⭐
6	Chinese translation for SAC doc	⭐
7	Best practice doc for multiple reward	⭐⭐
8	Chinese README	⭐⭐
9	RLHF overview doc	⭐⭐⭐
10	Best practice doc for customizing policy	⭐⭐⭐

Efficiency Section

No.	Task Name	Difficulty	Assigned to	Supporter	Status	Other Info
1	Integration for torch.compile	⭐⭐
2	Integration for torch.amp	⭐⭐
3	Integration for JAX env lib gymnax	⭐⭐

Code Quality Section

No.	Task Name	Difficulty	Assigned to	Supporter	Status	Other Info
1	Add more common typing lint type	⭐
2	Add deprecated function decorator	⭐	@ooooo-create	@PaParaZz1	Finish	reference link
3	Simplify SAC related policies	⭐⭐⭐

Test and Deploy Section

No.	Task Name	Difficulty	Assigned to	Supporter	Status	Other Info
1	Deployment of drone env docker	⭐

💖 If you are interested, you can claim a task by replying to this issue in the following format:

Metric No. : <The Task No. you claim>
Status :  Apply | Submit | Finish
Links : The repo links you fork (Apply status) / The PR links you open (Submit status)

✨ Thank you in advance to anyone who helps out! For some outstanding contributors, we will send them some souvenirs, like badge and T-shirt powered by OpenDILab.

Notes

1. The documation of DI-engine can be found at: https://di-engine-docs.readthedocs.io/en/latest/index.html
2. The contributing guides can be found at: https://github.com/opendilab/DI-engine/blob/main/CONTRIBUTING.md
3. If you have more detailed problems, you can join our slack channel. Slack has an IRC bridge as well as a range of apps which makes idling and answering questions super easy.

[GoingMyWay]

Hi, I would like to implement Algorithm Section 1 and 4. Here is my profile: https://qiuwei888.github.io/

Metric No. : Algorithm Section 1 and 4
Status : Apply
Links : TBD

[TuTuHuss]

Metric No. : Doc and Tutorial Section No.1
Status : Apply
Links : opendilab/DI-engine-docs#232

[PaParaZz1]

Hi, I would like to implement Algorithm Section 1 and 4. Here is my profile: https://qiuwei888.github.io/

Metric No. : Algorithm Section 1 and 4 Status : Apply Links : TBD

Thanks for your application! Which task do you want to start first? Algorithm Section 1 needs some understanding about the data flow of DI-engine while Algorithm Section 3 requires more necessary knowledge about multi-agent RL. You can choose one first and open a draft PR, we will provide corresponding support.

[GoingMyWay]

Hi, I would like to implement Algorithm Section 1 and 4. Here is my profile: https://qiuwei888.github.io/
Metric No. : Algorithm Section 1 and 4 Status : Apply Links : TBD

Thanks for your application! Which task do you want to start first? Algorithm Section 1 needs some understanding about the data flow of DI-engine while Algorithm Section 3 requires more necessary knowledge about multi-agent RL. You can choose one first and open a draft PR, we will provide corresponding support.

@PaParaZz1 Thanks. I would like select Algorithm Section 1 first. I have over 5 years of RL but I am a beginner of DI-Engine . I will look into the data flow of DI-engine and open the PR.

[deepNet-Chirag]

Hello @PaParaZz1! I would like to work with DI-Engine.. As I am new to it, I would like to start with Doc and Tutorial Translation.

Metric No. : Doc and Tutorial Section No. 2
Status : Apply
Links : opendilab/DI-engine-docs#235

[deepNet-Chirag]

Hey @PaParaZz1!
Here is the pull request thread link for Doc and Tutorial Section No. 2 : opendilab/DI-engine-docs#235

Let me know if there is any issue regarding the same. If everything is good then I would like to apply for the section no. 3.

Metric No. : Doc and Tutorial Section No. 3
Status : Apply
Links : TBD

[RajeshDM]

Hi @PaParaZz1, I am interested in working on the GNN + RL from the "Env + Application" Section. Could you please provide some details on what the contribution would entail

I am a Ph.D. student working with graph neural networks and classical AI planning (and have experience with RL).

Regards,
Rajesh Mangannavar

[PommesPeter]

I would like to do some translation work first because I am also new to the DI-engine. Meanwhile, I also try to learn something about RL or MARL for my research direction. I previously made some contributions to Paddle in terms of operator implementation.

Metric No. : Doc and Tutorial Section No. 4
Status : Finish
Links : https://github.com/opendilab/DI-engine-docs/pull/260/files

[ooooo-create]

Metric No. : Code Quality Section No. 2
Status : Submit
Links : DI-engine/pull/778